metadata
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-kk-sp2n-b16-ms1600-s
results: []
whisper-kk-sp2n-b16-ms1600-s
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2659
- Wer: 274.5556
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 1600
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.9302 | 0.18 | 800 | 0.3010 | 229.3416 |
| 0.83 | 0.37 | 1600 | 0.2659 | 274.5556 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3